MATLAB程序计算的经典数学问题：最短

java编写的贝叶斯网络分类器（貌似没有模型构建和参数学习过程）-java prepared by the Bayesian network classifier (seemingly no model of the learning process and parameters)

模拟退火基本模块，其中在尺度变换部分应用到了类似模拟退火算法部分，所有变量均使用汉语拼音很好懂-Simulated Annealing basic module, in which part of the scale transformation is applied to a similar part of simulated annealing algorithm, all variables are very good to understand the use of Hanyu Pinyin

BOLTZMAN（vc＋＋编写的程序神经网络程序）

本程序为基于工艺参数优化的改进遗传算法程序-based on the procedures for the optimization of process parameters improved genetic algorithm

遗传算法中的简单遗传算法，用matlab实现。-genetic algorithm simple genetic algorithm, using Matlab to achieve.

遗传算法编程很有用的，可以用来借鉴参考，希望对大家有帮助！-Genetic algorithm programming useful, can be used to draw reference to all of us want to help!

遗传算法与工程设计-Genetic Algorithms and Engineering Design

4。《演化程序――遗传算法和数据编码的结合》，[英]米凯利维兹着 科学出版社 2000年第一版 本书分三个部分共16章分别介绍了:1.遗传算法的概念、数学原理及方法步骤 2.遗传算法和数据编码联系起来所构成的演化程序 3.演化程序面向一些实际问题的应用。 本书语言生动，结构合理，较少使用专业性术语和深涩词汇，适合面临优化问题的研究生、程序员、设计师、工程师及科研工作人员参考。-4. "Evolutionary process-- genetic coding algorithm and data integration," [E] Mikhail Liweici a 520-531 2000 version of the first book in three parts a total of 16 chapters were introduced : 1. Genetic Algorithm concept mathematical principles and methods of Step 2. genetic algorithms and data coding linked posed by the evolution of procedures 3. Evolution-oriented procedures some of the practical problems of application. The book vivid language, reasonable structure, and less use of professional terminology and vocabulary deep acerbic suitable for optimization problems facing graduate students, programmers, designers, engineers and research personnel.

matlab编写的BP神经网络算法，的一个应用小程序-matlab prepared by BP neural network algorithm, a small process applications

以黎曼几何为理论依据，基于S.Amari的修正核函数思想提出了两种新的保角变换，用其对核函数进行数据依赖性改进，进一步提高支持向量机分类器泛化能力。以人工非线性分类问题 为对象进行研究，仿真实验结果表明采用新保角映射可以快速显著地改善分类器泛化性能，而且能大幅度地减少支持向量的数目。-Two novel conformal transformations were proposed based on the Riemannian geometry theory and S.Amari’sidea.And the kernel function was modified by the transformation in a data-dependent way.Our experimental results for theartificial nonlinear data set show that the generalization performance of support vector machines classifier is improvedremarkably and the number of support vectors is decreased greatly.